Have a personal or library account? Click to login
Super-resolution Reconstruction Based on Capsule Generative Adversarial Network Cover

Super-resolution Reconstruction Based on Capsule Generative Adversarial Network

International Journal of Advanced Network, Monitoring and Controls
Volume 7 (2022): Issue 4 (January 2022)
By: Ziyi Wu,  Hongge Yao,  Hualong Yang,  Hong Jiang,  Wei Zhang and  Jun Yu  
Open Access
|May 2023

Figures & Tables

Figure 1.

Structure diagram of CSRGAN.
Structure diagram of CSRGAN.

Figure 2.

Structure diagram of RDB.
Structure diagram of RDB.

Figure 3.

u is n 8-dimensional vectors obtained by encapsulating and flattening the data through the PrimaryCaps layer, v1 is a 16-dimensional digital capsule vector after a routing process and v2 is the 32-dimensional vector output at the end of the second routing process. wij is the fully connected weight matrix of the connected vector. The vectors u' and v' are the prediction vectors of u and v1 obtained through a linear hierarchical relationship, the subscripts i, j correspond to the number of vector u and the next layer vector v1, respectively. The parameter bij is the log prior probability from the lower capsule to the upper capsule. The parameter bij is the logarithmic prior probability from the low-level capsule to the high-level capsule and is used to update each cij correspondingly. cij is the coupling coefficient connecting the two layers' vectors before and after, representing the degree of correlation between the i-th vector of the previous layer and the j-th vector of the next layer. Squash is a linear rectification function, which normalizes the results obtained.
u is n 8-dimensional vectors obtained by encapsulating and flattening the data through the PrimaryCaps layer, v1 is a 16-dimensional digital capsule vector after a routing process and v2 is the 32-dimensional vector output at the end of the second routing process. wij is the fully connected weight matrix of the connected vector. The vectors u' and v' are the prediction vectors of u and v1 obtained through a linear hierarchical relationship, the subscripts i, j correspond to the number of vector u and the next layer vector v1, respectively. The parameter bij is the log prior probability from the lower capsule to the upper capsule. The parameter bij is the logarithmic prior probability from the low-level capsule to the high-level capsule and is used to update each cij correspondingly. cij is the coupling coefficient connecting the two layers' vectors before and after, representing the degree of correlation between the i-th vector of the previous layer and the j-th vector of the next layer. Squash is a linear rectification function, which normalizes the results obtained.

Figure 4.

Panda.
Panda.

Figure 5.

Rome.
Rome.

Figure 6.

Nut.
Nut.

Figure 7.

Train PSNR is evaluated on Set5.
Train PSNR is evaluated on Set5.

Figure 8.

The Roman Colosseum(a).
The Roman Colosseum(a).

Figure 9.

The Roman Colosseum(b).
The Roman Colosseum(b).

Figure 10.

castle(a).
castle(a).

Figure 11.

castle(b).
castle(b).

PSNR and SSIM

MethodBicubicSRCNNSRGANRDNCSRGAN
PSNR28.3930.4529.4332.4432.58
SSIM0.81020. 86160.84770.89880.9003
DOI: https://doi.org/10.2478/ijanmc-2022-0038 | Journal eISSN: 2470-8038
Journal RSS Feed
Language: English
Page range: 69 - 81
Published on: May 26, 2023
Published by: Xi’an Technological University
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year
Keywords:
Generative Adversarial Network,
Capsule Network,
Capsule Generative Adversarial Network,
Capsule Discriminator,
Super-resolution Reconstruction
Related subjects:
Computer sciences,
Computer sciences, other

© 2023 Ziyi Wu, Hongge Yao, Hualong Yang, Hong Jiang, Wei Zhang, Jun Yu, published by Xi’an Technological University
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Previous articleVolume 7 (2022): Issue 4 (January 2022)Next article